The least-squares goodness-of-fit parameter S' for all reflection
               data, after the final cycle of least squares. This parameter
               explicitly includes the restraints applied in the least-squares
               process. See also the definition of
               _refine.ls_goodness_of_fit_all.
                    (   sum   |w    |Yobs  - Ycalc|2| )1/2
                    ( + sumr|wr |Pcalc - Ptarg|2| )
               S' = ( ------------------------------------- )
                    (      Nref + Nrestr - Nparam     )
               Yobs   = the observed coefficients
                          (see _refine.ls_structure_factor_coef)
               Ycalc  = the observed coefficients
                          (see _refine.ls_structure_factor_coef)
               w        = the least-squares reflection weight
                          [1/(e.s.d. squared)]
               Pcalc  = the calculated restraint values
               Ptarg  = the target restraint values
               wr     = the restraint weight
               Nrefr  = the number of reflections used in the refinement
                          (see _refine.ls_number_reflns_obs)
               Nrestr = the number of restraints
                          (see _refine.ls_number_restraints)
               Nparam = the number of refined parameters
                          (see _refine.ls_number_parameters)
               sum  is taken over the specified reflection data
               sumr is taken over the restraint data